Diagnose Before You Prescribe

I was invited to sit on a panel this morning: "AI in Action: The Mindset Behind the Moves," at Auxiom's Community Appreciation Event, attended by 120 business leaders in Detroit Metro. Grateful to Founder and CEO Matt Loria for the invite. Auxiom is a local IT and cybersecurity company.

Before the panel, Ashok Sivanand (Nous) ran the room through a workflow-redesign workshop. He opened with a stat from McKinsey: 80% of companies doing generative AI work saw no change in profitability. He paired it with another: only 1 in 5 companies had actually redesigned a workflow before pointing AI at it. Same 1 in 5, both times. He called it a coincidence. This is similar data I referenced in David's Corner, The Tool is 10 Percent.

His worksheet was amazing though: name the constraint, name the workflow, name your customer, find the leak, pick one fix, run a 30-day experiment with a guardrail and a report-back date. His line on the handout: diagnose before you prescribe. All 120 execs walked out of that room with a real next step; that's rare for many speakers.

On the panel, I got to talk about an idea I've been writing about here: AI does two different jobs. It's good at mining your own record for what's already true, and it's good at amplifying whatever you give it. Skip straight to amplifying, and the output sounds like everyone else's.

Someone asked what my own transition looked like, going from a 12-person team to running alongside 20-plus specialists. Two years chasing tools before I found ICM. Two weeks after that, I converted all my unstructured data into structured markdown and built my routing map and orchestrator, Duke.

After, a CIO on the panel asked me how I was able to orchestrate across 50k markdown files. I said, "Simple: a map, and dropped Jake Van Clief and ICM as the solution."

The closing session was Aaron Salko and Kelly Johnson on human performance. A line I wrote down: "Technology creates capability; human performance determines the outcome". If you've got performance gaps today, AI doesn't fix them. It multiplies them across more people.

Stayed and talked with Ashok for a while after everything wrapped. The lesson he wanted to teach but didn't have time for: define what success looks like before you build or deploy, not after. Too many of us try to rationalize what we've built after we've built it, instead of setting up a proper eval before we start.

Anyway, I just wanted to share this experience with all of you and thank this community for all I've learned over the last 6-8 months. I would not have had the confidence without you all.

PS I couldn't wear the cowboy hat because the event was at a country club with a strict dress code.

16 comments

Diagnose Before You Prescribe